RLHF, PPO & GRPO Explained: A Top-Down Guide to LLM Policy Optimization
1:07:41
YouTubeMei Li
RLHF, PPO & GRPO Explained: A Top-Down Guide to LLM Policy Optimization
A top-down, self-contained walkthrough of how large language models are optimized with reinforcement learning. Starting from the core intuition, connecting it to the math, and then walking through one full training step for both PPO and GRPO — so you come away with a clear mental model of how each method optimizes an LLM policy. A note on ...
3 views1 month ago
RLCS
RLCS 2v2 | MAIN STREAM | EUROPE | CHAMPIONSHIP SUNDAY | RLCS 2026
5:57:15
RLCS 2v2 | MAIN STREAM | EUROPE | CHAMPIONSHIP SUNDAY | RLCS 2026
YouTubeRocket League Esports
182.1K views1 month ago
RLCS 1v1 | MAIN STREAM | NORTH AMERICA | PLAYOFFS | RLCS 2026
6:48:01
RLCS 1v1 | MAIN STREAM | NORTH AMERICA | PLAYOFFS | RLCS 2026
YouTubeRocket League Esports
96.7K views2 weeks ago
✅DROPS GIVEAWAYS✅|🔴HOUSEATHON DAY 3🔴|🔥RLCS TOP 8 WATCH PARTY🔥
11:54:59
✅DROPS GIVEAWAYS✅|🔴HOUSEATHON DAY 3🔴|🔥RLCS TOP 8 WATCH PARTY🔥
YouTubeJamaicanCoconut
61.7K views20 hours ago
Top videos
L4 TRPO and PPO (Foundations of Deep RL Series)
25:21
L4 TRPO and PPO (Foundations of Deep RL Series)
YouTubePieter Abbeel
51.2K viewsAug 25, 2021
PPO (Proximal Policy Optimization) Explained Simply – RL Algorithm Breakdown
1:25:33
PPO (Proximal Policy Optimization) Explained Simply – RL Algorithm Breakdown
YouTubeParvin Razzaghi
103 views1 month ago
Proximal Policy Optimization (PPO) - How to train Large Language Models
38:24
Proximal Policy Optimization (PPO) - How to train Large Language Models
YouTubeLuis Serrano Academy
86.6K viewsJan 24, 2024
Rocket League Montage
Rocket League, but every game your hitbox gets LONGER
32:52
Rocket League, but every game your hitbox gets LONGER
YouTubeLethamyr
292.1K views1 week ago
ROCKET LEAGUE INSANITY 118 ! (BEST GOALS, FREESTYLE CLIPS!)
10:25
ROCKET LEAGUE INSANITY 118 ! (BEST GOALS, FREESTYLE CLIPS!)
YouTubeROCKET LEAGUE FX
56.4K views1 week ago
Rocket League, but EVERY game I split the field into 4 different zones
19:20
Rocket League, but EVERY game I split the field into 4 different zones
YouTubeLethamyr
33.7K views1 week ago
L4 TRPO and PPO (Foundations of Deep RL Series)
25:21
Find in video from 01:23Policy Optimization Problem
L4 TRPO and PPO (Foundations of Deep RL Series)
51.2K viewsAug 25, 2021
YouTubePieter Abbeel
PPO (Proximal Policy Optimization) Explained Simply – RL Algorithm Breakdown
1:25:33
PPO (Proximal Policy Optimization) Explained Simply – RL Algorithm Breakdown
103 views1 month ago
YouTubeParvin Razzaghi
Proximal Policy Optimization (PPO) - How to train Large Language Models
38:24
Proximal Policy Optimization (PPO) - How to train Large Language Models
86.6K viewsJan 24, 2024
YouTubeLuis Serrano Academy
How Do You Stop an RL Agent From Destroying Itself? (PPO, Explained)
0:47
How Do You Stop an RL Agent From Destroying Itself? (PPO, Explained)
74 views3 weeks ago
YouTubeMLSlops
[UCLA RL-LLM] Chapter 1.4: Deep policy gradient methods (PPO, GRPO)
1:13:30
[UCLA RL-LLM] Chapter 1.4: Deep policy gradient methods (PPO, GRPO)
2.1K viewsJul 10, 2025
YouTubeErnest Ryu
[Road to Reasoning #4] Let's Move Beyond REINFORCE: Actor-Critic and PPO Algorithms Explained
31:48
[Road to Reasoning #4] Let's Move Beyond REINFORCE: Actor-Critic and PPO Algorithms Explained
36 views1 month ago
YouTubeAlex Eduardo Sanchez
Simply Explaining Proximal Policy Optimization (PPO) | Deep Reinforcement Learning
31:15
Simply Explaining Proximal Policy Optimization (PPO) | Deep Reinforcement Learning
28K viewsApr 11, 2025
YouTubeJohnny Code
8:31
Proximal Policy Optimization in Reinforcement Learning Simplified
40 views3 months ago
YouTubeRITEC AI Tech
9:21
PPO Explained: The Default Policy Gradient Algorithm Behind RLHF and AI Agents
28 views1 month ago
YouTubeEngineering Insider
45:35
Preference Alignment & RLHF in LLMs Explained | RLHF, PPO, DPO, ORPO, RL Basics & Practical Part-1
1.6K views1 month ago
YouTubeSunny Savita
8:50
PPO Coding | Proximal Policy Optimization (PPO) Code implementation | PPO in RL
535 viewsMar 5, 2025
YouTubeAILinkDeepTech
8:12
Why PPO Replaced TRPO as the Default RL Algorithm
5 views3 weeks ago
YouTubeMLSlops
4:42:34
4 Months of RL in 4 Hours | Deep Reinforcement Learning Course (PPO, DQN, SAC, A2C)
1.3K views6 months ago
YouTubeMadhav Malhotra
0:34
PPO Algorithm Explained 🤖 | Proximal Policy Optimization in Reinforcement Learning
202 views4 months ago
YouTubeQybrenthak AI Pvt. Ltd.
2:04:29
Introduction to Reinforcement Learning and PPO for robotics | VLA for autonomous driving series
2.4K views1 month ago
YouTubeVizuara
1:28:15
[Road to Reasoning #5] Let's Build PPO From Scratch! Using JAX & Flax NNX
171 views1 month ago
YouTubeAlex Eduardo Sanchez
9:00
GDPO Explained: NVIDIA Fixes GRPO for LLM Reinforcement Learning
3.7K views5 months ago
YouTubeAI Papers Academy
See more
Static thumbnail place holder